Human Motion Generation Using Variational Recurrent Neural Network
Human Motion Generation Using Variational Recurrent Neural Network
复制标题
DOI：
10.1145/3529570.3529588
复制
发表时间：
2022-02
期刊：
影响因子：
--
通讯作者：
Makoto Murakami;Takahiro Ikezawa
中科院分区：
文献类型：
--
作者：
Makoto Murakami;Takahiro Ikezawa
人体运动控制、编辑和合成是制作3D电脑图形视频游戏或电影的重要任务，因为在大多数游戏或电影中，有些角色的行为与人类相似。本研究的目的是建立一个能够产生各种自然字符动作的系统。在本研究中，我们认为人体运动产生的过程是复杂的、非线性的，可以用深度神经网络来建模。由于无法直接观察到运动生成过程（深度神经网络参数），需要通过学习运动捕捉系统记录的可观察到的人体运动数据来估计运动生成过程。另一方面，与生成相反的推理过程也用深度神经网络来表达。对人体运动数据进行推理和生成，并根据推理和生成过程应获得原始运动的准则对两种深度神经网络的参数进行优化。在本研究中，我们使用递归神经网络和变分自编码器构建了人体运动生成模型，并证实了从低维潜在空间可以生成各种人体运动。
∗ Human motion control, edit, and synthesis are important tasks to create 3D computer graphics video games or movies, because some characters act like humans in most of them. The purpose of this study is to construct a system which can generate various natural character motions. In this study, we consider that the process of human motion generation is complicated and non-linear, and it can be modeled by deep neural network. Since the motion generation process (deep neural network parameters) cannot be observed directly, it needs to be estimated by learning from observable human motion data recorded by motion capture system. On the other hand, the process of inference which is opposite to the generation is also expressed by deep neural network. And inference and generation are performed for human motion data, and the parameters of the both deep neural networks are optimized based on the criteria that the original motion should be obtained through inference and generation processes. In this study, we constructed a human motion generative model using recurrent neural network and variational autoencoders, and confirmed that various human motions can be generated from a low-dimensional latent space.